{
  "results": {
    "kobest_boolq": {
      "acc": 0.6004273504273504,
      "acc_stderr": 0.013076733548156574,
      "macro_f1": 0.5383070602365428,
      "macro_f1_stderr": 0.01360326947457233
    },
    "kobest_copa": {
      "acc": 0.789,
      "acc_stderr": 0.012909130321042099,
      "macro_f1": 0.7887412079797753,
      "macro_f1_stderr": 0.012915850547665574
    },
    "kobest_hellaswag": {
      "acc": 0.5,
      "acc_stderr": 0.022383074051792257,
      "acc_norm": 0.586,
      "acc_norm_stderr": 0.02204949796982787,
      "macro_f1": 0.49550311762225463,
      "macro_f1_stderr": 0.02234977157067147
    },
    "kobest_sentineg": {
      "acc": 0.924433249370277,
      "acc_stderr": 0.013281757903323496,
      "macro_f1": 0.9242944317315027,
      "macro_f1_stderr": 0.013286696883726102
    }
  },
  "versions": {
    "kobest_boolq": 0,
    "kobest_copa": 0,
    "kobest_hellaswag": 0,
    "kobest_sentineg": 0
  },
  "config": {
    "model": "gpt2",
    "model_args": "pretrained=/home/work/.folder/DeepSpeedExamples-master/applications/DeepSpeed-Chat/training/step3_rlhf_finetuning/output/actor/",
    "num_fewshot": 10,
    "batch_size": "8",
    "device": "cuda:0",
    "no_cache": true,
    "limit": null,
    "bootstrap_iters": 100000,
    "description_dict": {}
  }
}